Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    choosing strategy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     It
    0.52
    0
    0.51
     demarcation
    0.47
    1
    0.46
     propagation
    0.46
     acrylic
    0.46
    :
    0.46
     vitro
    0.46
     plasticity
    0.46
     touch
    0.45
    POSITIVE LOGITS
    Siempre
    0.48
    醎
    0.48
    鞑
    0.48
    偪
    0.47
    Chọn
    0.47
    estabelecimento
    0.46
    ㅍ
    0.45
    大赛
    0.45
    Choisissez
    0.44
     excused
    0.43
    Act Density 0.012%

    No Known Activations